Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tokenization-related elements in structured document formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.82
    GOTREF
    -0.72
    enterOuterAlt
    -0.61
    IsContent
    -0.60
    offsetof
    -0.58
     OnTriggerEnter
    -0.58
    UniformLocation
    -0.56
     SIMBAD
    -0.54
     <<<<<<<<<<<<<<
    -0.52
    DropColumn
    -0.52
    POSITIVE LOGITS
    ">//
    0.67
     linkovi
    0.63
     protoimpl
    0.56
    __*/
    0.56
    ⎨
    0.56
    riwal
    0.55
    ついで
    0.54
    ResponseWriter
    0.53
     //$
    0.53
     Descent
    0.53
    Act Density 0.007%

    No Known Activations